# Months against flights counts
# for the whole data points df_inv (7,009,728 rows), against on_time (5,330,292 rows),
# df_inv_15 (1,524,733 rows) , airline_cancelled (137,434 rows)
fig , ax = plt.subplots(2,2,sharex=True,figsize=(15,18))
#ax = ax.flatten()
plt.suptitle('Months flights counts (from highest) and proportions \nfor the year 2008',
fontsize=22,color='#BF1B00',
#x=.45,
y=.955)#y=1.08)
# first subplot
# Total flights per months
ax[0,0] = plt.subplot(2,2,1)
month_counts = df_inv['Month'].value_counts()
sns.countplot(data = df_inv, y = 'Month',
order = month_counts.index,
color = sns.color_palette('rocket')[1],
#sns.color_palette('vlag')[-1],#sns.color_palette('rocket')[0],#default_color,
ax=ax[0,0])
sns.set(font_scale=1.19,style='white')
sns.despine(bottom=True)
plt.title('Totals \n[7,009,724 flights]',fontsize=21,color='#AD1FFF',y=1.023)#x=.45,y=1.0365)
plt.xlabel('')
plt.ylabel('Month',fontsize=18)#weight='bold',
plt.xticks([])
# get the current tick locations and labels
locs, labels = plt.yticks(weight='bold')
# loop through each pair of locations and labels
for loc, label in zip(locs, labels):
# get the text property for the label to get the correct count
count = month_counts[label.get_text()]
percentage_total = 100*count/7009724
string = str(f"{count:,}") + "\n{:0.2f}%".format(percentage_total) #+ ' flights'
# print the annotation next to the bar
plt.text(count+3000, loc, s= string, va = 'center', color = 'black');
#########
# second subplot
# on-time flights by Months
ax[0,1] = plt.subplot(2,2,2)
month_counts = on_time['Month'].value_counts()
sns.set(font_scale=1.19,style='white')
sns.despine(bottom=True)
sns.countplot(data = on_time, y = 'Month',
order = month_counts.index,
color = sns.color_palette('vlag')[0],#sns.color_palette('viridis')[-3],# 'skyblue',
ax=ax[0,1])
plt.title('On-time \n[5,330,292 flights]',fontsize=21,color='#AD1FFF',y=1.023)#,x=.25
plt.xlabel('')
plt.ylabel('')
#plt.ylabel('Month',weight='bold',fontsize=18)
plt.xticks([])
plt.yticks(color = default_color)
# Recalculating the total flights counts for months
month_flights_count_whole = df_inv['Month'].value_counts() # to be used in calculating percentages of month flights
# counts with delays of 15 minutes or more
# against month total flights number
# get the current tick locations and labels
locs, labels = plt.yticks(weight='bold')
# loop through each pair of locations and labels
for loc, label in zip(locs, labels):
# get the text property for the label to get the correct count
count = month_counts[label.get_text()]
count_whole = month_flights_count_whole[label.get_text()]
percentage_value = 100*count/count_whole
percentage_total = 100*count/5330292
string = str(f"{count:,}") + " ({:0.2f}% of month's)\n{:0.2f}%".format(percentage_value,percentage_total)# flights
# print the annotation next to the bar
plt.text(count+3000, loc, s=string, va = 'center', color = 'black');
##################################
# third subplot
# delayed flights by Months
ax[1,0] = plt.subplot(2,2,3)
sns.set(font_scale=1.19,style='white')
sns.despine(bottom=True)
month_counts = df_inv_15['Month'].value_counts()
sns.countplot(data = df_inv_15, y = 'Month',
order = month_counts.index,
color = 'skyblue',
ax=ax[1,0])
plt.title('Delayed\n(15 min. arrival delay or more)\n[1,524,733 flights] ',fontsize=21,color='#AD1FFF',y=1.023)
#,x=.45,y=1.0365)
#,y=1.023)#,x=.25
plt.xlabel('')
plt.ylabel('')
plt.ylabel('Month',fontsize=18)#weight='bold',
plt.xticks([])
plt.yticks(color = 'brown')
# Recalculating the total flights counts for months
month_flights_count_whole = df_inv['Month'].value_counts() # to be used in calculating percentages of month flights
# counts with delays of 15 minutes or more
# against month total flights number
# get the current tick locations and labels
locs, labels = plt.yticks(weight='bold')
# loop through each pair of locations and labels
for loc, label in zip(locs, labels):
# get the text property for the label to get the correct count
count = month_counts[label.get_text()]
count_whole = month_flights_count_whole[label.get_text()]
percentage_value = 100*count/count_whole
percentage_total = 100*count/1524733
string = str(f"{count:,}") + " ({:0.2f}% of month's)\n{:0.2f}%".format(percentage_value,percentage_total)# flights
# print the annotation next to the bar
plt.text(count+3000, loc, s=string, va = 'center', color = 'black');
#################
# fourth subplot
# cancelled flights by Months
ax[1,1] = plt.subplot(2,2,4)
sns.set(font_scale=1.19,style='white')
sns.despine(bottom=True)
month_counts = airline_cancelled['Month'].value_counts()
sns.countplot(data = airline_cancelled ,
y = 'Month',
order = month_counts.index,
color = sns.color_palette()[1],
ax=ax[1,1])
plt.title('Cancelled \n[137,434 flights]',fontsize=21,color='#AD1FFF',y=1.0365)#x=.45,y=1.0365)#x=.205,y=1.0365)
plt.xlabel('')
plt.ylabel('')
#plt.ylabel('Month',weight='bold',fontsize=18)
plt.xticks([])
plt.yticks(color = sns.color_palette()[1],fontsize=12.5)
# Recalculating the total flights counts for months
month_flights_count_whole = df_inv['Month'].value_counts() # to be used in calculating percentages of month flights
# counts with delays of 15 minutes or more
# against month total flights number
# get the current tick locations and labels
locs, labels = plt.yticks(weight='bold')
# loop through each pair of locations and labels
for loc, label in zip(locs, labels):
# get the text property for the label to get the correct count
count = month_counts[label.get_text()]
count_whole = month_flights_count_whole[label.get_text()]
percentage_value = 100*count/count_whole
percentage_total = 100*count/137434
string = str(f"{count:,}") + " ({:0.2f}% of month's)\n{:0.2f}%".format(percentage_value,percentage_total)# flights
# print the annotation next to the bar
plt.text(count+3000, loc, s=string, va = 'center', color = 'black');#,fontsize=12.5);
#########
plt.subplots_adjust(wspace=0.35);
